Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.constants.io/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Every tool you create is automatically available through multiple interfaces — all with the same security, credential handling, and audit trail.
InterfaceHow It Works
Web UIGenerated form with file upload, streaming logs, and artifact download
Slack BotMention the bot in Slack to run tools conversationally
Agent ChatBuilt-in AI assistant that discovers and runs your tools
MCPModel Context Protocol endpoint for any MCP-compatible AI agent
REST APIProgrammatic POST /v1/run/[toolName] for automation

​
Slack Bot

​
Installation

  1. Go to your workspace settings in Constants
  2. Click Connect Slack
  3. Authorize the Constants bot for your Slack workspace

​
Usage

Mention the bot in any channel or thread: 
@Constants process this CSV with the report generator

​
How It Works

1

Mention Detected

Slack notifies Constants. The bot posts a “Working on it…” message immediately.
2

Context Gathered

If the mention is in a thread, the bot reads recent messages for context, enabling multi-turn interactions.
3

Tool Executed

The AI determines which tool to use, runs it in a secure sandbox, and collects results.
4

Results Posted

The bot updates its message with formatted results — structured output with clear formatting.

​
Thread Conversations

The Slack bot supports multi-turn interactions within threads: 
User: @Constants what tools do I have for data processing?
Bot: You have these tools available: CSV Processor, JSON Transformer, Report Generator...

User: @Constants run the CSV processor on the Q4 sales data with region=APAC
Bot: ✅ Processed 3,847 rows. 1,204 matched region=APAC.

​
Agent Chat

​
What Is It?

Constants includes a built-in AI assistant that can discover your tools, understand what they do, and run them in multi-step workflows.

​
How to Use

  1. Open the Agent tab from the sidebar
  2. Start a new conversation or continue an existing one
  3. Ask the agent to find and run tools, analyze results, or chain multiple tools together

​
Capabilities

The agent sees all tools you own and tools shared with you. Ask “what tools do I have?” or describe what you need — it finds the right one.
The agent runs tools in the same secure sandboxes as the UI. Results include full output, artifacts, and run logging.
Attach files to chat messages. The agent auto-maps them to tool input fields by file type. If required files are missing, it asks for them.
The agent maintains conversation context across turns. Chain tool executions, ask follow-up questions, or refine parameters based on output.

​
MCP (Model Context Protocol)

​
What Is It?

MCP is an open protocol for AI agents to discover and execute tools. Every Constants tool is automatically exposed as an MCP tool — no extra configuration needed.

​
Setup

Add the Constants MCP server to your agent or IDE configuration: 
{
  "mcpServers": {
    "constants": {
      "url": "https://constants.io/api/mcp",
      "apiKey": "YOUR_API_KEY"
    }
  }
}

​
How It Works

  1. Discovery — Agent calls tools/list to see all available tools (owned + shared)
  2. Execution — Agent calls tools/call with tool name and arguments
  3. Results — Output returned with the same structure as UI execution
MCP executions use the same sandbox, credential resolution, and logging as every other interface.

​
REST API (V1)

​
Overview

For programmatic access and automation: 
curl -X GET https://constants.io/api/v1/tools \
  -H "Authorization: Bearer YOUR_API_KEY"

curl -X POST https://constants.io/api/v1/run/my_tool_abc123 \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"param1": "value1"}'

​
Key Endpoints

MethodEndpointDescription
GET/v1/toolsList tools with schemas
POST/v1/run/:toolNameExecute a tool (waits up to 50s)
GET/v1/skill/:toolNameGet tool documentation as markdown
GET/v1/skills/searchSearch available tools
See the API Reference for full details.

​
API Keys

All programmatic interfaces (REST API, MCP, Slack bot) use API keys for authentication.

​
Creating Keys

  1. Click your profile icon → API Keys
  2. Click Create New Key
  3. Choose scopes:
    • mcp:read — List tools and view schemas
    • mcp:execute — Execute tools

​
Key Security

  • Keys are hashed before storage — Constants never stores the plain key
  • Each key has configurable scopes for least-privilege access
  • Keys can be revoked individually at any time
  • Usage is tracked per-key for auditing

​
Access & Governance

​
Tool Visibility

Access LevelWho Can See/Run
OwnerThe user who created the tool
SharedSpecific users added via email
WorkspaceAll members of the tool’s workspace
FeaturedPublic discovery (admin-curated)

​
Consistent Across Interfaces

Regardless of how a tool is triggered:
  • Same credential resolution and injection
  • Same secure sandbox with the same resource limits
  • Same run logging with full context
  • Same quota accounting against the workspace

​
What’s Next?

API Reference

Full API documentation with examples

Features Overview

See everything Constants can do